Update app.py

app.py

@@ -289,40 +289,50 @@ elif section == 'Forecasts Quality':
     
     # Time series for last 1 week
     last_week = data.loc[data.index >= (data.index[-1] - pd.Timedelta(days=7))]
-    st.write('The below plots show the time series of forecasts vs. observations provided by the ENTSO-E Transparency platform from the past week.')
-
-    num_per_var=2
-
-    forecast_columns_line=forecast_columns
+    st.write('The below plot shows the time series of forecasts vs. observations provided by the ENTSO-E Transparency platform from the past week.')
+    
+    # Options for selecting the data to display
+    variable_options = {
+        "Load": ("Load_entsoe", "Load_forecast_entsoe"),
+        "Solar": ("Solar_entsoe", "Solar_forecast_entsoe"),
+        "Wind Onshore": ("Wind_onshore_entsoe", "Wind_onshore_forecast_entsoe"),
+        "Wind Offshore": ("Wind_offshore_entsoe", "Wind_offshore_forecast_entsoe")
+    }
+    
+    # Dropdown to select the variable
+    selected_variable = st.selectbox("Select Variable for Line PLot", list(variable_options.keys()))
 
-    for i in range(0, len(forecast_columns_line), num_per_var):
-        actual_col = forecast_columns_line[i]
-        forecast_col = forecast_columns_line[i + 1]
+    # Get the corresponding columns for the selected variable
+    actual_col, forecast_col = variable_options[selected_variable]
 
-        if forecast_col in data.columns:
-            fig = go.Figure()
-            fig.add_trace(go.Scatter(x=last_week.index, y=last_week[actual_col], mode='lines', name='Actual'))
-            fig.add_trace(go.Scatter(x=last_week.index, y=last_week[forecast_col], mode='lines', name='Forecast ENTSO-E'))
-            fig.update_layout(title=f'Forecasts vs Actual for {actual_col}', xaxis_title='Date', yaxis_title='Value [MW]')
-        
-            st.plotly_chart(fig)
+    # Plot only the selected variable's data
+    fig = go.Figure()
+    fig.add_trace(go.Scatter(x=last_week.index, y=last_week[actual_col], mode='lines', name='Actual'))
+    fig.add_trace(go.Scatter(x=last_week.index, y=last_week[forecast_col], mode='lines', name='Forecast ENTSO-E'))
+    fig.update_layout(title=f'Forecasts vs Actual for {selected_variable}', xaxis_title='Date', yaxis_title='Value [MW]')
     
+    st.plotly_chart(fig)
 
     # Scatter plots for error distribution
     st.subheader('Error Distribution')
     st.write('The below scatter plots show the error distribution of all three fields: Solar, Wind and Load between the selected date range')
-    data_2024 = data[data.index.year > 2023]
-    for i in range(0, len(forecast_columns), 2):
-        actual_col = forecast_columns[i]
-        forecast_col = forecast_columns[i + 1]
-        if forecast_col in data_2024.columns:
-            obs = data_2024[actual_col]
-            pred = data_2024[forecast_col]
-            error = pred - obs
+    selected_variable = st.selectbox("Select Variable for Error Distribution", list(variable_options.keys()))
+
+    # Get the corresponding columns for the selected variable
+    actual_col, forecast_col = variable_options[selected_variable]
 
-            fig = px.scatter(x=obs, y=pred, labels={'x': 'Observed [MW]', 'y': 'Predicted by ENTSO-E [MW]'})
-            fig.update_layout(title=f'Error Distribution for {forecast_col}')
-            st.plotly_chart(fig)
+    # Filter data for the selected year and check if columns are available
+    data_2024 = data[data.index.year > 2023]
+    if forecast_col in data_2024.columns:
+        obs = data_2024[actual_col]
+        pred = data_2024[forecast_col]
+        
+        # Calculate error and plot
+        error = pred - obs 
+        fig = px.scatter(x=obs, y=error, labels={'x': 'Observed [MW]', 'y': 'Error of Forecast ENTSO-E [MW]'})
+        fig.update_layout(title=f'Error Distribution for {selected_variable}')
+        
+        st.plotly_chart(fig)
 
     
         
@@ -358,50 +368,83 @@ elif section == 'Forecasts Quality':
     accuracy_metrics.sort_values(by=accuracy_metrics.columns[1], ascending=True, inplace=True)
     accuracy_metrics = accuracy_metrics.round(4)
 
-    col1, col2 = st.columns([3, 2])
+    col1, col2 = st.columns([1, 2])
 
     with col1:
+        st.markdown(
+            """
+            <style>
+            .small-chart {
+                margin-top: 30px;  /* Adjust this value as needed */
+            }
+            </style>
+            """,
+            unsafe_allow_html=True
+        )
         st.dataframe(accuracy_metrics)
-
-    with col2:
-        st.markdown("""
+        st.markdown(
+            """
             <style>
-            .big-font {
-                font-size: 20px;
-                font-weight: 500;
+            .small-chart {
+                margin-top: -30px;  /* Adjust this value as needed */
             }
             </style>
-            <div class="big-font">
-            Equations
-            </div>
-            """, unsafe_allow_html=True)
+            """,
+            unsafe_allow_html=True
+        )
 
-        st.markdown(r"""
-        $\text{MAE} = \frac{1}{n}\sum_{i=1}^{n}|y_i - \hat{y}_i|$
+    with col2:
         
-                    
-        $\text{rMAE} = \frac{\text{MAE}}{MAE_{\text{Persistence Model}}}$
-                    
-        """)
-
+        # Prepare data for the radar chart
+        rmae_values = accuracy_metrics['rMAE'].tolist()
+        categories = accuracy_metrics.index.tolist()
+        
+        fig = go.Figure()
+        fig.add_trace(go.Scatterpolar(
+            r=rmae_values,
+            theta=categories,
+            fill='toself',
+            name='rMAE'
+        ))
+        
+        # Configuring radar chart layout to be smaller
+        fig.update_layout(
+            width=250,  # Adjust width
+            height=250,  # Adjust height
+            margin=dict(t=20, b=20, l=0, r=0),  # Remove all margins
+            polar=dict(
+                radialaxis=dict(
+                    visible=True,
+                    range=[0, max(rmae_values) * 1.2]  # Adjust range dynamically
+                )),
+            showlegend=False
+        )
+        
+        # Apply CSS class to remove extra space above chart
+        st.plotly_chart(fig, use_container_width=True, config={'displayModeBar': False}, className="small-chart")
 
     st.subheader('ACF plots of Errors')
     st.write('The below plots show the ACF (Auto-Correlation Function) for the errors of all three data fields obtained from ENTSO-E: Solar, Wind and Load.')
 
-    for i in range(0, len(forecast_columns), 2):
-        actual_col = forecast_columns[i]
-        forecast_col = forecast_columns[i + 1]
-        if forecast_col in data.columns:
-            obs = data[actual_col]
-            pred = data[forecast_col]
-            error = pred - obs
+    # Dropdown to select the variable
+    selected_variable = st.selectbox("Select Variable for ACF of Errors", list(variable_options.keys()))
+
+    # Get the corresponding columns for the selected variable
+    actual_col, forecast_col = variable_options[selected_variable]
+
+    # Calculate the error and plot ACF if columns are available
+    if forecast_col in data.columns:
+        obs = data[actual_col]
+        pred = data[forecast_col]
+        error = pred - obs
 
-            st.write(f"**ACF of Errors for {actual_col}**")
-            fig, ax = plt.subplots(figsize=(10, 5))
-            plot_acf(error.dropna(), ax=ax)
-            st.pyplot(fig)
+        st.write(f"**ACF of Errors for {selected_variable}**")
+        fig, ax = plt.subplots(figsize=(10, 5))
+        plot_acf(error.dropna(), ax=ax)
+        st.pyplot(fig)
 
-            acf_values = acf(error.dropna(), nlags=240)
+        # Optionally calculate and store ACF values for further analysis if needed
+        acf_values = acf(error.dropna(), nlags=240)
         
 # Section 3: Insights
 elif section == 'Insights':
@@ -427,6 +470,20 @@ elif section == 'Insights':
     st.pyplot(pairplot_fig)
 
 elif selected_country == 'Overall':
+    st.markdown(
+        """
+        <style>
+        .main-container {
+            padding-top: 0px;  /* Remove extra padding at the top */
+        }
+        .chart-spacing {
+            margin-top: -40px;  /* Adjust this value to control spacing between map and radar plot */
+        }
+        </style>
+        """,
+        unsafe_allow_html=True
+    )
+
     st.subheader("Net Load Error Map")
     st.write("""
         The net load error map highlights the error in the forecasted versus actual net load for each country. 
@@ -440,7 +497,7 @@ elif selected_country == 'Overall':
             filter_df = df[forecast_columns].dropna()
             net_load = filter_df['Load_entsoe'] - filter_df['Wind_onshore_entsoe'] - filter_df['Wind_offshore_entsoe'] - filter_df['Solar_entsoe']
             net_load_forecast = filter_df['Load_forecast_entsoe'] - filter_df['Wind_onshore_forecast_entsoe'] - filter_df['Wind_offshore_forecast_entsoe'] - filter_df['Solar_forecast_entsoe']
-            error = (net_load - net_load_forecast).iloc[-1]
+            error = (net_load_forecast - net_load).iloc[-1]
             date = filter_df.index[-1].strftime("%Y-%m-%d %H:%M")  # Get the latest date in string format
             return error, date
 
@@ -514,6 +571,7 @@ elif selected_country == 'Overall':
 
     # Call the function to plot the map
     plot_net_load_error_map(data_dict)
+    # CSS to adjust layout and remove extra spacing
 
     st.subheader("rMAE of Forecasts published on ENTSO-E TP")
     st.write("""